add evaluations

evals/hellaswag/hellaswag_nl_Llama-2-7b-chat-hf.json

@@ -0,0 +1,23 @@
+{
+  "results": {
+    "hellaswag_nl": {
+      "acc": 0.38866702644360496,
+      "acc_stderr": 0.005064405668097518,
+      "acc_norm": 0.48515920129519696,
+      "acc_norm_stderr": 0.005192533901850712
+    }
+  },
+  "versions": {
+    "hellaswag_nl": 1
+  },
+  "config": {
+    "model": "hf-auto",
+    "model_args": "pretrained=meta-llama/Llama-2-7b-chat-hf,use_accelerate=True,device_map_option=auto,dtype=bfloat16,load_in_8bit=True",
+    "batch_size": "auto",
+    "device": "cuda",
+    "no_cache": false,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "description_dict": {}
+  }
+}

evals/hellaswag/hellaswag_nl_Llama-2-7b-hf.json

@@ -0,0 +1,23 @@
+{
+  "results": {
+    "hellaswag_nl": {
+      "acc": 0.3951430113329736,
+      "acc_stderr": 0.005079304286040443,
+      "acc_norm": 0.5141932002158661,
+      "acc_norm_stderr": 0.005192729334278779
+    }
+  },
+  "versions": {
+    "hellaswag_nl": 1
+  },
+  "config": {
+    "model": "hf-auto",
+    "model_args": "pretrained=meta-llama/Llama-2-7b-hf,use_accelerate=True,device_map_option=auto,dtype=bfloat16,load_in_8bit=True",
+    "batch_size": "auto",
+    "device": "cuda",
+    "no_cache": false,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "description_dict": {}
+  }
+}